mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-12 08:42:18 +00:00
style(loadtest): keep the new sustained workloads in the existing layout
This commit is contained in:
narmstrong-berry
parent
c8edea05f0
commit
2bb4905f5f
4 changed files with 44 additions and 248 deletions
|
|
@ -1,71 +1,20 @@
|
|||
{
|
||||
"name": "sustained 10 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
|
||||
"stages": [
|
||||
{
|
||||
"duration_s": 900,
|
||||
"rps": 10
|
||||
}
|
||||
],
|
||||
"stages": [{"duration_s": 900, "rps": 10}],
|
||||
"arrivals": "constant",
|
||||
"nonstream_max_s": 360,
|
||||
"warmup_s": 60,
|
||||
"max_in_flight": 30000,
|
||||
"keys": {
|
||||
"file": "out/keys.txt",
|
||||
"zipf_s": 0
|
||||
},
|
||||
"models": {
|
||||
"chat": {
|
||||
"prefix": "gpt-6-astra-",
|
||||
"count": 10
|
||||
},
|
||||
"messages": {
|
||||
"prefix": "claude-opus-5-5-",
|
||||
"count": 10
|
||||
}
|
||||
},
|
||||
"keys": {"file": "out/keys.txt", "zipf_s": 0},
|
||||
"models": {"chat": {"prefix": "gpt-6-astra-", "count": 10}, "messages": {"prefix": "claude-opus-5-5-", "count": 10}},
|
||||
"classes": [
|
||||
{
|
||||
"name": "chat",
|
||||
"weight": 1,
|
||||
"endpoint": "chat",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "messages",
|
||||
"weight": 1,
|
||||
"endpoint": "messages",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
}
|
||||
{"name": "chat", "weight": 1, "endpoint": "chat", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}},
|
||||
{"name": "messages", "weight": 1, "endpoint": "messages", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,71 +1,20 @@
|
|||
{
|
||||
"name": "sustained 25 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
|
||||
"stages": [
|
||||
{
|
||||
"duration_s": 900,
|
||||
"rps": 25
|
||||
}
|
||||
],
|
||||
"stages": [{"duration_s": 900, "rps": 25}],
|
||||
"arrivals": "constant",
|
||||
"nonstream_max_s": 360,
|
||||
"warmup_s": 60,
|
||||
"max_in_flight": 30000,
|
||||
"keys": {
|
||||
"file": "out/keys.txt",
|
||||
"zipf_s": 0
|
||||
},
|
||||
"models": {
|
||||
"chat": {
|
||||
"prefix": "gpt-6-astra-",
|
||||
"count": 10
|
||||
},
|
||||
"messages": {
|
||||
"prefix": "claude-opus-5-5-",
|
||||
"count": 10
|
||||
}
|
||||
},
|
||||
"keys": {"file": "out/keys.txt", "zipf_s": 0},
|
||||
"models": {"chat": {"prefix": "gpt-6-astra-", "count": 10}, "messages": {"prefix": "claude-opus-5-5-", "count": 10}},
|
||||
"classes": [
|
||||
{
|
||||
"name": "chat",
|
||||
"weight": 1,
|
||||
"endpoint": "chat",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "messages",
|
||||
"weight": 1,
|
||||
"endpoint": "messages",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
}
|
||||
{"name": "chat", "weight": 1, "endpoint": "chat", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}},
|
||||
{"name": "messages", "weight": 1, "endpoint": "messages", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,71 +1,20 @@
|
|||
{
|
||||
"name": "sustained 50 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
|
||||
"stages": [
|
||||
{
|
||||
"duration_s": 900,
|
||||
"rps": 50
|
||||
}
|
||||
],
|
||||
"stages": [{"duration_s": 900, "rps": 50}],
|
||||
"arrivals": "constant",
|
||||
"nonstream_max_s": 360,
|
||||
"warmup_s": 60,
|
||||
"max_in_flight": 30000,
|
||||
"keys": {
|
||||
"file": "out/keys.txt",
|
||||
"zipf_s": 0
|
||||
},
|
||||
"models": {
|
||||
"chat": {
|
||||
"prefix": "gpt-6-astra-",
|
||||
"count": 10
|
||||
},
|
||||
"messages": {
|
||||
"prefix": "claude-opus-5-5-",
|
||||
"count": 10
|
||||
}
|
||||
},
|
||||
"keys": {"file": "out/keys.txt", "zipf_s": 0},
|
||||
"models": {"chat": {"prefix": "gpt-6-astra-", "count": 10}, "messages": {"prefix": "claude-opus-5-5-", "count": 10}},
|
||||
"classes": [
|
||||
{
|
||||
"name": "chat",
|
||||
"weight": 1,
|
||||
"endpoint": "chat",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "messages",
|
||||
"weight": 1,
|
||||
"endpoint": "messages",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
}
|
||||
{"name": "chat", "weight": 1, "endpoint": "chat", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}},
|
||||
{"name": "messages", "weight": 1, "endpoint": "messages", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,71 +1,20 @@
|
|||
{
|
||||
"name": "sustained 75 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
|
||||
"stages": [
|
||||
{
|
||||
"duration_s": 900,
|
||||
"rps": 75
|
||||
}
|
||||
],
|
||||
"stages": [{"duration_s": 900, "rps": 75}],
|
||||
"arrivals": "constant",
|
||||
"nonstream_max_s": 360,
|
||||
"warmup_s": 60,
|
||||
"max_in_flight": 30000,
|
||||
"keys": {
|
||||
"file": "out/keys.txt",
|
||||
"zipf_s": 0
|
||||
},
|
||||
"models": {
|
||||
"chat": {
|
||||
"prefix": "gpt-6-astra-",
|
||||
"count": 10
|
||||
},
|
||||
"messages": {
|
||||
"prefix": "claude-opus-5-5-",
|
||||
"count": 10
|
||||
}
|
||||
},
|
||||
"keys": {"file": "out/keys.txt", "zipf_s": 0},
|
||||
"models": {"chat": {"prefix": "gpt-6-astra-", "count": 10}, "messages": {"prefix": "claude-opus-5-5-", "count": 10}},
|
||||
"classes": [
|
||||
{
|
||||
"name": "chat",
|
||||
"weight": 1,
|
||||
"endpoint": "chat",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "messages",
|
||||
"weight": 1,
|
||||
"endpoint": "messages",
|
||||
"stream_fraction": 0.5,
|
||||
"context_tokens": {
|
||||
"dist": "loguniform",
|
||||
"min": 10000,
|
||||
"max": 50000
|
||||
},
|
||||
"ttft_ms": {
|
||||
"dist": "uniform",
|
||||
"min": 200,
|
||||
"max": 800
|
||||
},
|
||||
"duration_s": {
|
||||
"dist": "uniform",
|
||||
"min": 1,
|
||||
"max": 5
|
||||
}
|
||||
}
|
||||
{"name": "chat", "weight": 1, "endpoint": "chat", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}},
|
||||
{"name": "messages", "weight": 1, "endpoint": "messages", "stream_fraction": 0.5,
|
||||
"context_tokens": {"dist": "loguniform", "min": 10000, "max": 50000},
|
||||
"ttft_ms": {"dist": "uniform", "min": 200, "max": 800},
|
||||
"duration_s": {"dist": "uniform", "min": 1, "max": 5}}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue